English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Learning and predicting the pose parameters of a 3D hand model given animage, such as locations of hand joints, is challenging due to large viewpointchanges and articulations, and severe self-occlusions exhibited particularly inegocentric views. Both feature learning and prediction modeling have beeninvestigated to tackle the problem. Though effective, most existingdiscriminative methods yield a single deterministic estimation of target poses.Due to their single-value mapping intrinsic, they fail to adequately handleself-occlusion problems, where occluded joints present multiple modes. In thispaper, we tackle the self-occlusion issue and provide a complete description ofobserved poses given an input depth image by a novel method called hierarchicalmixture density networks (HMDN). The proposed method leverages thestate-of-the-art hand pose estimators based on Convolutional Neural Networks tofacilitate feature learning, while it models the multiple modes in a two-levelhierarchy to reconcile single-valued and multi-valued mapping in its output.The whole framework with a mixture of two differentiable density functions isnaturally end-to-end trainable. In the experiments, HMDN produces interpretableand diverse candidate samples, and significantly outperforms thestate-of-the-art methods on two benchmarks with occlusions, and performscomparably on another benchmark free of occlusions.

Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network